6 citations · 10 across the 13 of their papers we have counts for
18 papers
The Value of Memory in Language Agents
Zehao Lin, Erenkai Zhu, Helan Hu +3
Memory enables language agents to carry useful distinctions from past experience into future decisions. Its value depends on which distinctions survive, whether a bounded agent can…
Compiling Autoregressive LLM Control into Policy-Exact Parallel Inference for Hierarchical RAG
Zehao Lin, Qianfeng Shen, Xixuan Hao +8
Large language models increasingly act as controllers in structured decision pipelines, yet their decisions are still executed by autoregressive text decoding. Hierarchical RAG is…
Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localization
Yutian Jiang, Ruijie Li, Sisuo Lyu +4
Open-world geo-localization requires models to reason over ambiguous visual cues through multi-step reasoning and external knowledge grounding. While recent large vision-language m…
CoST: Semantic-Aware Urban Understanding via Spatial-Temporal Alignment
Yutian Jiang, Jiabo Liu, Xixuan Hao +1
Geospatial representation learning from satellite imagery is a fundamental problem for large-scale urban analysis and real-world applications. Despite recent advances, current meth…
Metis: Memory Foundation Model
Zeyu Zhang, Ziliang Guo, Yihang Sun +14
Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reaso…
Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling
Xixuan Hao, Yutian Jiang, Jiabo Liu +4
Urban region profiling constitutes a core problem in urban computing, supporting applications such as population estimation, economic assessment, and environmental monitoring. Exis…
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
Xixuan Hao, Zeyu Zhang, Zehao Lin +6
Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing benchmarks, however, evaluate…
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
Zehao Lin, Xixuan Hao, Renyu Fu +5
The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, ch…
Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web
Xixuan Hao, Guicheng Li, Daiqiang Wu +6
The proliferation of ride-hailing services has fundamentally transformed urban mobility patterns, making accurate ride-hailing forecasting crucial for optimizing passenger experien…
AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing
Xusen Guo, Mingxing Peng, Xixuan Hao +4
Web-based participatory urban sensing has emerged as a vital approach for modern urban management by leveraging mobile individuals as distributed sensors. However, existing urban s…
Select, then Balance: Exploring Exogenous Variable Modeling of Spatio-Temporal Forecasting
Wei Chen, Yuqian Wu, Yuanshao Zhu +4
Spatio-temporal (ST) forecasting is critical for dynamic systems, yet existing methods predominantly rely on modeling a limited set of observed target variables. In this paper, we…
Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems
Xingchen Zou, Yuhao Yang, Zheng Chen +4
We introduce Traffic-R1, a 3B-parameter foundation model with human-like reasoning for Traffic signal control (TSC), developed via self-exploration and iterative reinforcement of L…
Geospatial Representation Learning: A Survey from Deep Learning to The LLM Era
Xixuan Hao, Yutian Jiang, Xingchen Zou +6
The ability to transform location-centric geospatial data into meaningful computational representations has become fundamental to modern spatial analysis and decision-making. Geosp…
Advancing Medical Radiograph Representation Learning: A Hybrid Pre-training Paradigm with Multilevel Semantic Granularity
Hanqi Jiang, Xixuan Hao, Yuzhou Huang +4
This paper introduces an innovative approach to Medical Vision-Language Pre-training (Med-VLP) area in the specialized context of radiograph representation learning. While conventi…
Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs
Xingchen Zou, Jiani Huang, Xixuan Hao +6
Regional socioeconomic indicators are critical across various domains, yet their acquisition can be costly. Inferring global socioeconomic indicators from a limited number of regio…
UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation
Siru Zhong, Xixuan Hao, Yibo Yan +3
Urbanization challenges underscore the necessity for effective satellite image-text retrieval methods to swiftly access specific information enriched with geographic semantics for…
UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction
Xixuan Hao, Wei Chen, Yibo Yan +4
Urban socioeconomic indicator prediction aims to infer various metrics related to sustainable development in diverse urban landscapes using data-driven methods. However, prevalent…
Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook
Xingchen Zou, Yibo Yan, Xixuan Hao +8
As cities continue to burgeon, Urban Computing emerges as a pivotal discipline for sustainable development by harnessing the power of cross-domain data fusion from diverse sources…